Issues

• [Feature]: optional diagnostics entry that runs Pantheon (active GPU stress with a pass/fail exit code)

  NVIDIA/cluster-readiness-engine#554 · Filter by author saqibkh opened on Oct 22, 2026
  1

• [Bug]: Multi-node nemotron5 training with enableCheckpoint fails: megatron-clone init containers race on the shared workspace

  NVIDIA/cluster-readiness-engine#548 · Filter by author Rico00121 opened on Oct 21, 2026
  2

• captureTimeoutLog never finds the MPI launcher, so a timed-out NCCL Job records a worker's log

  NVIDIA/cluster-readiness-engine#546 · Filter by author asivanadi0 opened on Oct 21, 2026

• Run the launcher's worker-reachability wait on every MPI path, and fail the launcher without retries

  NVIDIA/cluster-readiness-engine#545 · Filter by author asivanadi0 opened on Oct 21, 2026

• [Bug]: OCI workload pods reference a hard-coded network-operator/sriov-net NAD that AICR clusters do not have

  NVIDIA/cluster-readiness-engine#542 · Filter by author mlsorensen opened on Oct 21, 2026

• [Bug]: nvcrectl workflow render has no mock nodes for akamai or nscale

  bugneeds-triage
  NVIDIA/cluster-readiness-engine#538 · Filter by author kaynetu opened on Oct 20, 2026
  2

  

• [Feature]: Deleting a Certification should wait until its workloads have stopped

  NVIDIA/cluster-readiness-engine#522 · Filter by author asivanadi0 opened on Oct 19, 2026

• [Feature]: A run-level deadline for a Certification

  NVIDIA/cluster-readiness-engine#521 · Filter by author asivanadi0 opened on Oct 19, 2026

• [Bug]: Chart value manager.image.pullPolicy is ignored; the Deployment never sets imagePullPolicy

  bugneeds-triage
  NVIDIA/cluster-readiness-engine#511 · Filter by author kaynetu opened on Oct 16, 2026
  3

• [Bug]: a stale reconcile can overwrite a terminal Workflow condition after a status conflict

  bug
  NVIDIA/cluster-readiness-engine#509 · Filter by author ndipebot opened on Oct 16, 2026
  1

• [Bug]: A failing NCCL launcher crash-loops for ~7 minutes before NVCRE reports WorkloadFailed

  bugneeds-triage
  NVIDIA/cluster-readiness-engine#498 · Filter by author kaynetu opened on Oct 15, 2026
  2

• [Feature]: Export final NCCL bandwidth results as metrics (gauges are deleted when the measurement completes)

  NVIDIA/cluster-readiness-engine#475 · Filter by author Rico00121 opened on Oct 10, 2026
  3

• [Bug]: Bandwidth threshold and report use different BusBW numbers (max across message sizes vs largest size). Which one is canonical?

  NVIDIA/cluster-readiness-engine#472 · Filter by author asivanadi0 opened on Oct 10, 2026

• [Bug]: Clique summary counts every failed node of a multi-rack group against its first rack (wrong rack blamed, negative node counts)

  NVIDIA/cluster-readiness-engine#471 · Filter by author asivanadi0 opened on Oct 10, 2026

• [Bug]: Multi-iteration runs lose earlier-iteration failures: node listed as both succeeded and failed, generic IterationsFailed reason, report shows only the last iteration

  NVIDIA/cluster-readiness-engine#470 · Filter by author asivanadi0 opened on Oct 10, 2026
  1

• Surface a workload whose workers never become Ready instead of waiting out timeoutPerJob

  enhancement
  NVIDIA/cluster-readiness-engine#469 · Filter by author ndipebot opened on Oct 9, 2026
  4

• [Feature]: Fail Job bandwidth thresholds at once when the measurement completes without final results

  NVIDIA/cluster-readiness-engine#450 · Filter by author asivanadi0 opened on Oct 8, 2026

• [Feature]: Add native JUnit XML output for certification results

  enhancement
  NVIDIA/cluster-readiness-engine#446 · Filter by author supertetelman opened on Oct 7, 2026

• [Bug]: Workflow name suffix omits most CategoryOptions, so sibling categories can collide and report each other's results

  NVIDIA/cluster-readiness-engine#430 · Filter by author wussh opened on Oct 4, 2026
  2

  

• [Feature]: Optional Trainer and JobSet dependencies in the NVCRE Helm chart

  NVIDIA/cluster-readiness-engine#429 · Filter by author Rico00121 opened on Oct 3, 2026
  1

• [Feature]: Support Network Operator east-west networks

  enhancement
  NVIDIA/cluster-readiness-engine#400 · Filter by author kreeuwijk opened on Sep 30, 2026
  2

• Publish the chart's CRDs as a separate cluster-readiness-engine-crds chart

  NVIDIA/cluster-readiness-engine#357 · Filter by author lockwobr opened on Sep 18, 2026
  

• Close the env-laundering class in TestAttestPredicateUsesOnlyTrustedContext with a sentinel harness

  enhancementgithub_actionssecurity
  NVIDIA/cluster-readiness-engine#339 · Filter by author ndipebot opened on Sep 11, 2026
  2

• Bring Makefile and workflow tool pins under automated updates

  github_actionssecurity
  Task

  NVIDIA/cluster-readiness-engine#279 · Filter by author mchmarny opened on Sep 2, 2026
  1

• Rekor signing-identity monitoring (stretch)

  enhancementgithub_actionssecurity
  Task

  NVIDIA/cluster-readiness-engine#275 · Filter by author mchmarny opened on Sep 2, 2026